v2.0.0

Add expanded test suite with Adam Smith vs George Adam Smith name collision examples; showcases golden eval set and how quantization can be decided through the eval lens

---

Archived on Zenodo after publish. Cite the concept DOI for latest, or this release's version DOI to pin the snapshot.

What's Changed

• Clarify toRoutingHint behavior in README documentation by @lukefwalton in #14
• Runnable int8 demo (demo/): mechanism + corpus build handoff by @lukefwalton in #15
• Add reproducible int8 scaling demo by @lukefwalton in #16
• demo: enforce top-slot contract; clarify rho and int4 scope by @lukefwalton in #17

Full Changelog: v1.5.0...v2.0.0

v1.5.0

Add: Next steps to aid future contributions, refined docs

---

Archived on Zenodo after publish. Cite the concept DOI for latest, or this release's version DOI to pin the snapshot.

What's Changed

• Document design boundaries and open problems in NEXT-STEPS.md by @lukefwalton in #12

Full Changelog: v1.4.0...v1.5.0

v1.4.0

Added section 7 to Answer Engine: A Small Reference Implementation for Citation-Grounded AI Answers; contribution guidelines

---

Archived on Zenodo after publish. Cite the concept DOI for latest, or this release's version DOI to pin the snapshot.

What's Changed

• docs: production-scaling notes for the empirical scope question by @lukefwalton in #10
• docs: add CONTRIBUTING.md (contribution scope) by @lukefwalton in #11

Full Changelog: v1.3.1...v1.4.0

v1.3.1

Doc addition + release will increment version in README now

---

Archived on Zenodo after publish. Cite the concept DOI for latest, or this release's version DOI to pin the snapshot.

What's Changed

• docs: warn that enrichment must not echo the gold query verbatim by @lukefwalton in #8
• ci: auto-bump the README release baseline on release by @lukefwalton in #9

Full Changelog: v1.3.0...v1.3.1

v1.3.0

Add related implementation document

---

Archived on Zenodo after publish. Cite the concept DOI for latest, or this release's version DOI to pin the snapshot.

What's Changed

• docs: add artifact note and wire citation metadata by @lukefwalton in #7

Full Changelog: v1.2.2...v1.3.0

v1.2.2

Adding P4's DOI

---

Archived on Zenodo after publish. Cite the concept DOI for latest, or this release's version DOI to pin the snapshot.

Full Changelog: v1.2.1...v1.2.2

v1.2.1

Documentation update with learnings from production

---

Archived on Zenodo after publish. Cite the concept DOI for latest, or this release's version DOI to pin the snapshot.

What's Changed

• Document evidence pruning, scope boundaries, and enrichment patterns by @lukefwalton in #6

Full Changelog: v1.2.0...v1.2.1

v1.2.0

citation metadata, .zenodo.json, release workflow

---

Archived on Zenodo after publish. Cite the concept DOI for latest, or this release's version DOI to pin the snapshot.

What's Changed

• Add citation metadata and release workflow by @lukefwalton in #4

Full Changelog: v1.1.0...v1.2.0

v1.1.0 — Targeted eval runs and report validation

Applying learnings from my production answer engine:

New:

• Stable gold query ids (q01–q10) for targeted runs
• npm run eval -- --ids, --from-report, --list, and --help
• JSON eval reports under artifacts/eval/ for rerunning failures
• forbidAnswerPatterns gold guard (e.g. no raw URLs in answer prose on boundary queries)
• Strict eval report validation before reruns (JSON syntax, result shape, count consistency)
• Reject aborted --fail-fast reports for --from-report

Docs:

• Eval workflow documented in eval/README.md
• README: retrieved-vs-cited UI lesson, repo positioning, related writing, Zenodo DOI
• Contribution guidance: “Code the invariant. Document the scaling pattern. Comment the footgun.”

No changes to the no-leak boundary or citation-grounding contract.

v1.0.0

Initial launch